Spaces:

mistralai
/

Voxtral-Realtime-WebGPU

Running

Error: failed to call OrtRun().

by JTRNS - opened Mar 23

Mar 23

Error: failed to call OrtRun(). ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/providers/webgpu/buffer_manager.cc:540 auto onnxruntime::webgpu::BufferManager::Download(WGPUBuffer, void *, size_t)::(lambda)::operator()(wgpu::MapAsyncStatus, wgpu::StringView) const status == wgpu::MapAsyncStatus::Success was false. Failed to download data from buffer: Failed to execute 'mapAsync' on 'GPUBuffer': A valid external Instance reference no longer exists.

Xenova

Mar 23

This probably means you ran out of GPU memory. What device are you using?

JTRNS

Mar 24

Specification	Value
GPU processor	Quadro T1000 with Max-Q Design
DirectX version	12.0
Driver version	595.79
Driver type	DCH
Direct3D feature level	12_1
CUDA cores	896
Core clock	1350 MHz
Memory data rate	10.00 Gbps
Memory interface	128-bit
Memory bandwidth	160.03 GB/s
Total available graphics memory	12189 MB
Dedicated video memory	4096 MB GDDR6
System video memory	0 MB
Shared system memory	8093 MB
Video BIOS version	90.17.53.00.49
IRQ	Not used
Bus	Unknown bus

While it is not a powerful card, I have been able to run almost every other WebGPU space on it. (Thank you for all that work btw!)

Closed all other tabs and made sure no other gpu intensive apps were running
While loading the model the 2 warning about powerPreference show up (I am on a windows machine)
I can start the transcription and it works fine for at most the first 15 seconds
After 15 seconds / 10 sentences text stream starts to slow down and lag (far) behind speech
The whole browser window flashes white for a second. So including address bar, bookmarks etc. etc. but not the windows native UI like taskbar.
The recording UI appears again, but this time with the error notification

Can't upload a .log file, so I just pasted the contents of the devtools console logs below.

Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'ambient-light-sensor'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'battery'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'document-domain'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'layout-animations'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'legacy-image-formats'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'oversized-images'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'vr'.
Voxtral-Realtime-WebGPU:102 Unrecognized feature: 'wake-lock'.
index-XIg_GcZm.js:12 Unable to determine content-length from response headers. Will expand buffer when needed.
warn @ index-XIg_GcZm.js:12
Gs @ index-XIg_GcZm.js:21
uc @ index-XIg_GcZm.js:21
await in uc
dc @ index-XIg_GcZm.js:21
await in dc
fc @ index-XIg_GcZm.js:21
pc @ index-XIg_GcZm.js:21
gm @ index-XIg_GcZm.js:33
from_pretrained @ index-XIg_GcZm.js:33
from_pretrained @ index-XIg_GcZm.js:33
from_pretrained @ index-XIg_GcZm.js:33
(anonymous) @ index-XIg_GcZm.js:44
Cd @ index-XIg_GcZm.js:8
(anonymous) @ index-XIg_GcZm.js:8
mn @ index-XIg_GcZm.js:8
kd @ index-XIg_GcZm.js:8
hp @ index-XIg_GcZm.js:9
pp @ index-XIg_GcZm.js:9
index-XIg_GcZm.js:12 The powerPreference option is currently ignored when calling requestAdapter() on Windows. See https://crbug.com/369219127
Nn @ index-XIg_GcZm.js:12
rr @ index-XIg_GcZm.js:12
init @ index-XIg_GcZm.js:12
await in init
re @ index-XIg_GcZm.js:9
ie @ index-XIg_GcZm.js:9
create @ index-XIg_GcZm.js:9
i @ index-XIg_GcZm.js:21
Promise.then
Kc @ index-XIg_GcZm.js:21
await in Kc
(anonymous) @ index-XIg_GcZm.js:33
await in (anonymous)
Dm @ index-XIg_GcZm.js:33
from_pretrained @ index-XIg_GcZm.js:33
await in from_pretrained
(anonymous) @ index-XIg_GcZm.js:44
Cd @ index-XIg_GcZm.js:8
(anonymous) @ index-XIg_GcZm.js:8
mn @ index-XIg_GcZm.js:8
kd @ index-XIg_GcZm.js:8
hp @ index-XIg_GcZm.js:9
pp @ index-XIg_GcZm.js:9
83052129-47c9-4ba6-8776-fbcf4a104846:79 The powerPreference option is currently ignored when calling requestAdapter() on Windows. See https://crbug.com/369219127
Ic @ 83052129-47c9-4ba6-8776-fbcf4a104846:79
$func10524 @ 055d3336:0xf063d7
$Md @ 055d3336:0x1013ddd
b @ 83052129-47c9-4ba6-8776-fbcf4a104846:44
od @ 83052129-47c9-4ba6-8776-fbcf4a104846:98
$func1642 @ 055d3336:0x1f292c
$func3980 @ 055d3336:0x5f194a
$func4771 @ 055d3336:0x71e78e
$func3458 @ 055d3336:0x4f6820
$ec @ 055d3336:0xaefecb
b @ 83052129-47c9-4ba6-8776-fbcf4a104846:44
(anonymous) @ 83052129-47c9-4ba6-8776-fbcf4a104846:3
Ut @ index-XIg_GcZm.js:12
Wt @ index-XIg_GcZm.js:12
Rn @ index-XIg_GcZm.js:12
ar @ index-XIg_GcZm.js:12
loadModel @ index-XIg_GcZm.js:12
createInferenceSessionHandler @ index-XIg_GcZm.js:12
create @ index-XIg_GcZm.js:9
await in create
i @ index-XIg_GcZm.js:21
Promise.then
Kc @ index-XIg_GcZm.js:21
await in Kc
(anonymous) @ index-XIg_GcZm.js:33
await in (anonymous)
Dm @ index-XIg_GcZm.js:33
from_pretrained @ index-XIg_GcZm.js:33
await in from_pretrained
(anonymous) @ index-XIg_GcZm.js:44
Cd @ index-XIg_GcZm.js:8
(anonymous) @ index-XIg_GcZm.js:8
mn @ index-XIg_GcZm.js:8
kd @ index-XIg_GcZm.js:8
hp @ index-XIg_GcZm.js:9
pp @ index-XIg_GcZm.js:9
index.html:1 A valid external Instance reference no longer exists.
index-XIg_GcZm.js:12 An error occurred during model execution: "Error: failed to call OrtRun(). ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/providers/webgpu/buffer_manager.cc:540 auto onnxruntime::webgpu::BufferManager::Download(WGPUBuffer, void *, size_t)::(lambda)::operator()(wgpu::MapAsyncStatus, wgpu::StringView) const status == wgpu::MapAsyncStatus::Success was false. Failed to download data from buffer: Failed to execute 'mapAsync' on 'GPUBuffer': A valid external Instance reference no longer exists.
".
error @ index-XIg_GcZm.js:12
km @ index-XIg_GcZm.js:33
await in km
oE @ index-XIg_GcZm.js:33
sE @ index-XIg_GcZm.js:33
await in sE
forward @ index-XIg_GcZm.js:33
generate @ index-XIg_GcZm.js:33
await in generate
generate @ index-XIg_GcZm.js:33
(anonymous) @ index-XIg_GcZm.js:44
index-XIg_GcZm.js:12 Inputs given to model: {input_features: {…}, attention_mask: {…}, position_ids: {…}, past_padding_cache: {…}, past_key_values.0.key: {…}, …}attention_mask: {type: 'int64', dims: Array(2), location: 'cpu', data: BigInt64Array(3460)}input_features: {type: 'float32', dims: Array(3), location: 'cpu', data: Float32Array(217088)}past_key_values.0.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.0.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.1.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.1.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.2.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.2.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.3.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.3.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.4.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.4.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.5.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.5.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.6.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.6.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.7.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.7.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.8.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.8.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.9.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.9.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.10.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.10.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.11.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.11.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.12.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.12.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.13.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.13.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.14.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.14.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.15.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.15.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.16.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.16.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.17.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.17.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.18.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.18.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.19.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.19.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.20.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.20.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.21.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.21.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.22.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.22.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.23.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.23.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.24.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.24.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.25.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.25.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.26.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.26.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.27.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.27.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.28.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.28.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.29.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.29.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.30.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.30.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.31.key: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_key_values.31.value: {type: 'float16', dims: Array(4), location: 'gpu-buffer'}past_padding_cache: {type: 'float16', dims: Array(3), location: 'cpu', data: Float16Array(2816)}position_ids: {type: 'int64', dims: Array(2), location: 'cpu', data: BigInt64Array(848)}[[Prototype]]: Object
error @ index-XIg_GcZm.js:12
km @ index-XIg_GcZm.js:33
await in km
oE @ index-XIg_GcZm.js:33
sE @ index-XIg_GcZm.js:33
await in sE
forward @ index-XIg_GcZm.js:33
generate @ index-XIg_GcZm.js:33
await in generate
generate @ index-XIg_GcZm.js:33
(anonymous) @ index-XIg_GcZm.js:44
index-XIg_GcZm.js:44 Transcription error: Error: failed to call OrtRun(). ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/providers/webgpu/buffer_manager.cc:540 auto onnxruntime::webgpu::BufferManager::Download(WGPUBuffer, void *, size_t)::(lambda)::operator()(wgpu::MapAsyncStatus, wgpu::StringView) const status == wgpu::MapAsyncStatus::Success was false. Failed to download data from buffer: Failed to execute 'mapAsync' on 'GPUBuffer': A valid external Instance reference no longer exists.

    at Pt (index-XIg_GcZm.js:11:30749)
    at Vn (index-XIg_GcZm.js:12:28334)
    at async fr.run (index-XIg_GcZm.js:12:35833)
    at async e.run (index-XIg_GcZm.js:9:55849)
    at async km (index-XIg_GcZm.js:33:17606)
    at async oE (index-XIg_GcZm.js:33:104436)
    at async sE (index-XIg_GcZm.js:33:105029)
    at async e.forward (index-XIg_GcZm.js:33:105967)
    at async e.generate (index-XIg_GcZm.js:33:40176)
    at async e.generate (index-XIg_GcZm.js:33:106441)
(anonymous) @ index-XIg_GcZm.js:44

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment